Bypassing LLM Watermarks with Color-Aware Substitutions

19 March 2024

Papers citing "Bypassing LLM Watermarks with Color-Aware Substitutions"

4 / 4 papers shown

Title
Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Yixin Cheng Hongcheng Guo Yangming Li Leonid Sigal AAML WaLM 59 0 0 08 May 2025
Can Watermarked LLMs be Identified by Users via Crafted Prompts? Aiwei Liu Sheng Guan Yong-Jin Liu L. Pan Yifei Zhang Liancheng Fang Lijie Wen Philip S. Yu Xuming Hu WaLM 123 2 0 04 Oct 2024
Large Language Model Watermark Stealing With Mixed Integer Programming Zhaoxi Zhang Xiaomei Zhang Yanjun Zhang Leo Yu Zhang Chao Chen Shengshan Hu Asif Gill Shirui Pan AAML 38 4 0 30 May 2024
Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models Hanlin Zhang Benjamin L. Edelman Danilo Francati Daniele Venturi G. Ateniese Boaz Barak WaLM 138 54 0 07 Nov 2023